Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4823 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.6026. Min Act: -0.0001

Data Index: 493605 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.6013. Min Act: -0.0001

Data Index: 625530 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.6013. Min Act: -0.0001

Data Index: 776359 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5103. Min Act: -0.0001

Data Index: 952622 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5227. Min Act: -0.0001

Data Index: 206589 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5137. Min Act: -0.0001

Data Index: 757598 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4830. Min Act: -0.0001

Data Index: 954823 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4331. Min Act: -0.0001

Data Index: 1315283 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4580. Min Act: -0.0001

Data Index: 560111 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4613. Min Act: -0.0001

Data Index: 1031662 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4437. Min Act: -0.0001

Data Index: 426746 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4516. Min Act: -0.0001

Data Index: 409025 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4573. Min Act: -0.0001

Data Index: 62034 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4387. Min Act: -0.0001

Data Index: 557722 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4384. Min Act: -0.0001

Data Index: 1347516 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4471. Min Act: -0.0001

Data Index: 931453 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4426. Min Act: -0.0001

Data Index: 1063533 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4231. Min Act: -0.0001

Data Index: 201781 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4648. Min Act: -0.0001

Data Index: 967830 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4368. Min Act: -0.0001

Data Index: 2211 (C4 (Web Text))

Max Activating Token Index: 390